Multi-model fusion driven eye movement tracking method and system for mobile equipment

Abstract

The invention discloses a multi-model fusion driven eye movement tracking method for mobile equipment. The method comprises the following steps: (1) eye movement characteristic analysis based on an appearance model; (2) eye movement data mapping based on a feature model; and (3) eye movement fixation point calculation based on multi-model fusion. The invention further provides a multi-model fusion driven eye movement tracking system for the mobile equipment. The system comprises the following modules which are sequentially connected and feed data: an eye movement feature analysis module basedon an appearance model; an eye movement data mapping module based on the feature model; and an eye movement fixation point calculation module based on multi-model fusion. The eye movement tracking method on the current mobile device is expanded, and the eye movement tracking precision, the calculation speed and the stability of the mobile device in a complex interaction environment are improved.

Description

technical field [0001] The invention relates to an eye movement tracking method and system. Background technique [0002] Commonly used eye-tracking methods mainly include appearance model-based and feature-based models: the appearance-based eye-tracking method inputs the appearance image of the human eye, and then constructs a convolutional neural network as the appearance model to extract the unexplainable hidden features of the human eye image. Contains features, and then calculates the eye movement fixation point; the eye movement tracking method based on the feature model inputs clear and interpretable human eye image features, preprocesses the human eye image, extracts image features, and then establishes image features and eye movement fixation points The mapping equation between them is used to calculate the eye movement fixation point. The advantages and disadvantages of the two methods are as follows: The eye tracking method based on the appearance model has the a...

AI Technical Summary

Problems solved by technology

However, the current problems of mobile devices include: (1) limited hardware conditions, such as weak CPU processing power, low camera resolution, and small memory capacity; (2) complex use environment and large lighting changes

Images